Learning Category-Specific Dictionary and Shared Dictionary for Fine-Grained Image Categorization
This paper targets fine-grained image categorization by learning a category-specific dictionary for each category and a shared dictionary for all the categories. Such category-specific dictionaries encode subtle visual differences among different categories, while the shared dictionary encodes commo...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2016
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/82155 http://hdl.handle.net/10220/41143 |
| _version_ | 1826110962045812736 |
|---|---|
| author | Tsang, Ivor Wai-Hung Gao, Shenghua Ma, Yi |
| author2 | School of Computer Engineering |
| author_facet | School of Computer Engineering Tsang, Ivor Wai-Hung Gao, Shenghua Ma, Yi |
| author_sort | Tsang, Ivor Wai-Hung |
| collection | NTU |
| description | This paper targets fine-grained image categorization by learning a category-specific dictionary for each category and a shared dictionary for all the categories. Such category-specific dictionaries encode subtle visual differences among different categories, while the shared dictionary encodes common visual patterns among all the categories. To this end, we impose incoherence constraints among the different dictionaries in the objective of feature coding. In addition, to make the learnt dictionary stable, we also impose the constraint that each dictionary should be self-incoherent. Our proposed dictionary learning formulation not only applies to fine-grained classification, but also improves conventional basic-level object categorization and other tasks such as event recognition. Experimental results on five data sets show that our method can outperform the state-of-the-art fine-grained image categorization frameworks as well as sparse coding based dictionary learning frameworks. All these results demonstrate the effectiveness of our method. |
| first_indexed | 2024-10-01T02:43:08Z |
| format | Journal Article |
| id | ntu-10356/82155 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T02:43:08Z |
| publishDate | 2016 |
| record_format | dspace |
| spelling | ntu-10356/821552020-05-28T07:18:05Z Learning Category-Specific Dictionary and Shared Dictionary for Fine-Grained Image Categorization Tsang, Ivor Wai-Hung Gao, Shenghua Ma, Yi School of Computer Engineering Class-specific dictionary Shared dictionary This paper targets fine-grained image categorization by learning a category-specific dictionary for each category and a shared dictionary for all the categories. Such category-specific dictionaries encode subtle visual differences among different categories, while the shared dictionary encodes common visual patterns among all the categories. To this end, we impose incoherence constraints among the different dictionaries in the objective of feature coding. In addition, to make the learnt dictionary stable, we also impose the constraint that each dictionary should be self-incoherent. Our proposed dictionary learning formulation not only applies to fine-grained classification, but also improves conventional basic-level object categorization and other tasks such as event recognition. Experimental results on five data sets show that our method can outperform the state-of-the-art fine-grained image categorization frameworks as well as sparse coding based dictionary learning frameworks. All these results demonstrate the effectiveness of our method. ASTAR (Agency for Sci., Tech. and Research, S’pore) 2016-08-16T08:22:29Z 2019-12-06T14:47:41Z 2016-08-16T08:22:29Z 2019-12-06T14:47:41Z 2014 Journal Article Gao, S., Tsang, I. W.-H., & Ma, Y. (2014). Learning Category-Specific Dictionary and Shared Dictionary for Fine-Grained Image Categorization. IEEE Transactions on Image Processing, 23(2), 623-634. 1057-7149 https://hdl.handle.net/10356/82155 http://hdl.handle.net/10220/41143 10.1109/TIP.2013.2290593 en IEEE Transactions on Image Processing © 2013 IEEE. |
| spellingShingle | Class-specific dictionary Shared dictionary Tsang, Ivor Wai-Hung Gao, Shenghua Ma, Yi Learning Category-Specific Dictionary and Shared Dictionary for Fine-Grained Image Categorization |
| title | Learning Category-Specific Dictionary and Shared Dictionary for Fine-Grained Image Categorization |
| title_full | Learning Category-Specific Dictionary and Shared Dictionary for Fine-Grained Image Categorization |
| title_fullStr | Learning Category-Specific Dictionary and Shared Dictionary for Fine-Grained Image Categorization |
| title_full_unstemmed | Learning Category-Specific Dictionary and Shared Dictionary for Fine-Grained Image Categorization |
| title_short | Learning Category-Specific Dictionary and Shared Dictionary for Fine-Grained Image Categorization |
| title_sort | learning category specific dictionary and shared dictionary for fine grained image categorization |
| topic | Class-specific dictionary Shared dictionary |
| url | https://hdl.handle.net/10356/82155 http://hdl.handle.net/10220/41143 |
| work_keys_str_mv | AT tsangivorwaihung learningcategoryspecificdictionaryandshareddictionaryforfinegrainedimagecategorization AT gaoshenghua learningcategoryspecificdictionaryandshareddictionaryforfinegrainedimagecategorization AT mayi learningcategoryspecificdictionaryandshareddictionaryforfinegrainedimagecategorization |